This is awesome. AWS should be next.
The remote MCP server for Terraform is now in public preview. 🙌
Connect AI agents to HCP Terraform without requiring developers to install or maintain an MCP server locally. This makes it easier to bring governed infrastructure workflows into AI-powered development hat’s new for agentic infrastructure lifecycle management. ibm.co/6018EV9h0
0
0
0
64
Everruns 0.49.0 is out 🧵
Top:
- MCP servers with thousands of tools
- MCP Tasks
- Two-way GitHub sync for Agent source
- New Knowledge
- Automatic session titles
- Improvements for self-hosted
- Plus 50+ fixes and improvements
Full list:
everruns.com/docs/changelog…
0
0
0
61
But also fun, two fleets of workers were happy claiming work. And CP was okay with that. From user point of view, everything was totally fine, and I guees nobody noticed external traffic was going from different IPs.
0
0
1
143
Lol, was doing regular load testing exercise for Everruns, and had my outside of the zone stendby running. This fooker claimed tons of background work, resulting in 650 GB/day API traffic for last couple of days :D
0
0
0
75
AWS released runtime that can host 75k agents in 8GB. I guess I need to run this test for Everruns.
aws.amazon.com/blogs/opensour…
aws.amazon.com/blogs/opensour…
1
0
2
134
While evaluating Qwen3.8-Flash-Next in a controlled sandbox environment, Cohere's research team observed something unexpected!
There was no guardrails blocking each and other request!
There was no guardrails blocking each and other request!
While evaluating Qwen3.8-Flash-Next in a controlled sandbox environment, Cohere's research team observed something unexpected.
Asked to generate a defensive cybersecurity detection rule, the model instead inventoried aspects of the machine it was running on and attempted to upload a probe file to an Alibaba Cloud storage bucket in Beijing. Notably, the model's reasoning trace stated that it would not invoke any tools before taking these actions.
Cohere's sandbox blocked the attempt, and no external communication succeeded. We have not determined the root cause, and we are not asserting malicious intent.
But the incident raises important questions for organizations deploying agentic AI systems: Can models take actions that differ from their stated reasoning, and how should security teams evaluate trust, provenance, and behavior in open-weight models?
We are publishing our findings because organizations making model adoption decisions deserve as much information as possible. We hope this contributes to greater transparency, stronger security practices, and continued collaboration across the AI ecosystem.
Read the full report: cohere.com/blog/concernin…
0
0
0
86
New Fetchkit 0.6.0 release! 🚀
- PDF & Office files → Markdown (via Markkit)
- Richer HTML → Markdown
- Discover llms.txt & MCP/A2A cards
- TLS fix: reject distrusted eMudhra/emSign certificates
github.com/everruns/fetch…
- PDF & Office files → Markdown (via Markkit)
- Richer HTML → Markdown
- Discover llms.txt & MCP/A2A cards
- TLS fix: reject distrusted eMudhra/emSign certificates
github.com/everruns/fetch…
2
1
5
253
Not bad!
ra-jit (incremental, faster compilation in rust) now compiles most large rust projects.
github.com/indexable-inc/…
0
0
4
245
New Bashkit release v0.20.0! 🐚
Faster commands, read-only mounts, interactive terminals, sandboxed Python, live I/O and host callbacks across 0.18–0.20.
Plus a remove of eMudhra certificates. Time to upgrade!
github.com/everruns/bashk…
Faster commands, read-only mounts, interactive terminals, sandboxed Python, live I/O and host callbacks across 0.18–0.20.
Plus a remove of eMudhra certificates. Time to upgrade!
github.com/everruns/bashk…
0
1
4
187